Fehlerbehebung bei KI-Übersetzungen
- 1. Nicht alle Sprachen werden im Dialogfenster „Mit KI übersetzen“ angezeigt.
- 2. Das Glossar verwendet nicht immer den von mir zugewiesenen Glossarbegriff
- 3. Der Inhalt wird nicht übersetzt.
- 4. [en] What constitutes a token?
- 5. [en] Is there anything that does not count towards the token total?
- 6. [en] How many tokens are needed for a typical publication?
- 7. [en] Do (translated) terms from the glossary included in the text count towards tokens used?
- 8. [en] Do you offer refunds for AI translations if we are not happy with the quality of the translation?
1. | Nicht alle Sprachen werden im Dialogfenster „Mit KI übersetzen“ angezeigt. |
| |
2. | Das Glossar verwendet nicht immer den von mir zugewiesenen Glossarbegriff |
In einigen Fällen, in denen der KI-Übersetzungsdienst der Meinung ist, dass der Begriff im Glossar der Zielsprache zu sehr von seiner ursprünglichen Bedeutung abweicht, wird der Standardübersetzungsbegriff wiederhergestellt. Weitere Informationen finden Sie unter Glossare für KI-Übersetzungen. | |
3. | Der Inhalt wird nicht übersetzt. |
| |
4. | [en] What constitutes a token? |
[en] One token is equivalent to one character in the list below:
Anmerkung[en] Keep in mind that the token calculation is a rough estimate of the actual cost. | |
5. | [en] Is there anything that does not count towards the token total? |
[en] DocBook XML elements are not counted as characters. | |
6. | [en] How many tokens are needed for a typical publication? |
[en] While it is hard to say what a “typical” publication is, we can provide a rough guideline. Technical documentation in English normally uses slightly longer words than regular English texts (an average of around 6 characters per word compared to around 4 characters per word for regular texts). This means that a text of 1 million words would consume on average around 8 to 10 million tokens (at 6 characters per word, plus all spaces and punctuation). | |
7. | [en] Do (translated) terms from the glossary included in the text count towards tokens used? |
[en] While existing (approved) translations are by default not included in the content sent out for translation (and therefore are not included in the total character count), already translated glossary terms are included since they are required for the translation service to make sense of a sentence (i.e. you cannot have gaps in the middle of a sentence just because it's a term that has already been translated). Since these glossary terms by necessity need to be processed by the translation service, they do count toward the total character count and therefore will incur a token cost. Anmerkung[en] You can include already approved translations in your export by selecting “Include approved translations”. This does mean that they will count towards the total character count. | |
8. | [en] Do you offer refunds for AI translations if we are not happy with the quality of the translation? |
[en] Unfortunately, Paligo cannot take responsibility for the quality of third-party services. We therefore recommend that you start with the smallest token package and perform some real world tests to see if the quality of the translations meets your expectations. |